From: Sascha Hauer s.hauer@pengutronix.de

[ Upstream commit f5e1040196dbfe14c77ce3dfe3b7b08d2d961e88 ]

integrity_kernel_read() returns the number of bytes read. If this is a short read then this positive value is returned from ima_calc_file_hash_atfm(). Currently this is only indirectly called from ima_calc_file_hash() and this function only tests for the return value being zero or nonzero and also doesn't forward the return value. Nevertheless there's no point in returning a positive value as an error, so translate a short read into -EINVAL.

Signed-off-by: Sascha Hauer s.hauer@pengutronix.de Signed-off-by: Mimi Zohar zohar@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- security/integrity/ima/ima_crypto.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index d4c7b8e1b083d..7532b062be594 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -268,8 +268,11 @@ static int ima_calc_file_hash_atfm(struct file *file, rbuf_len = min_t(loff_t, i_size - offset, rbuf_size[active]); rc = integrity_kernel_read(file, offset, rbuf[active], rbuf_len); - if (rc != rbuf_len) + if (rc != rbuf_len) { + if (rc >= 0) + rc = -EINVAL; goto out3; + }

if (rbuf[1] && offset) { /* Using two buffers, and it is not the first

From: Jia-Ju Bai baijiaju1990@gmail.com

[ Upstream commit e2751463eaa6f9fec8fea80abbdc62dbc487b3c5 ]

In encode_attrs(), there is an if statement on line 1145 to check whether label is NULL: if (label && (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL))

When label is NULL, it is used on lines 1178-1181: *p++ = cpu_to_be32(label->lfs); *p++ = cpu_to_be32(label->pi); *p++ = cpu_to_be32(label->len); p = xdr_encode_opaque_fixed(p, label->label, label->len);

To fix these bugs, label is checked before being used.

These bugs are found by a static analysis tool STCheck written by us.

Signed-off-by: Jia-Ju Bai baijiaju1990@gmail.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs4xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 46a8d636d151e..ab07db0f07cde 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1174,7 +1174,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, } else *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } - if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { + if (label && (bmval[2] & FATTR4_WORD2_SECURITY_LABEL)) { *p++ = cpu_to_be32(label->lfs); *p++ = cpu_to_be32(label->pi); *p++ = cpu_to_be32(label->len);

From: Chuck Lever chuck.lever@oracle.com

[ Upstream commit 98ef77d1aaa7a2f4e1b2a721faa084222021fda7 ]

Eli Dorfman reports that after a series of idle disconnects, an RPC/RDMA transport becomes unusable (rdma_create_qp returns -ENOMEM). Problem was tracked down to increasing Send Queue size after each reconnect.

The rdma_create_qp() API does not promise to leave its @qp_init_attr parameter unaltered. In fact, some drivers do modify one or more of its fields. Thus our calls to rdma_create_qp must use a fresh copy of ib_qp_init_attr each time.

This fix is appropriate for kernels dating back to late 2007, though it will have to be adapted, as the connect code has changed over the years.

Reported-by: Eli Dorfman eli@vastdata.com Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sunrpc/xprtrdma/verbs.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 805b1f35e1caa..2bd9b4de0e325 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -605,10 +605,10 @@ void rpcrdma_ep_destroy(struct rpcrdma_xprt *r_xprt) * Unlike a normal reconnection, a fresh PD and a new set * of MRs and buffers is needed. */ -static int -rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, - struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) +static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, + struct ib_qp_init_attr *qp_init_attr) { + struct rpcrdma_ia *ia = &r_xprt->rx_ia; int rc, err;

trace_xprtrdma_reinsert(r_xprt); @@ -625,7 +625,7 @@ rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, }

rc = -ENETUNREACH; - err = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr); + err = rdma_create_qp(ia->ri_id, ia->ri_pd, qp_init_attr); if (err) { pr_err("rpcrdma: rdma_create_qp returned %d\n", err); goto out3; @@ -642,16 +642,16 @@ rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, return rc; }

-static int -rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, struct rpcrdma_ep *ep, - struct rpcrdma_ia *ia) +static int rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, + struct ib_qp_init_attr *qp_init_attr) { + struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rdma_cm_id *id, *old; int err, rc;

trace_xprtrdma_reconnect(r_xprt);

- rpcrdma_ep_disconnect(ep, ia); + rpcrdma_ep_disconnect(&r_xprt->rx_ep, ia);

rc = -EHOSTUNREACH; id = rpcrdma_create_id(r_xprt, ia); @@ -673,7 +673,7 @@ rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, struct rpcrdma_ep *ep, goto out_destroy; }

- err = rdma_create_qp(id, ia->ri_pd, &ep->rep_attr); + err = rdma_create_qp(id, ia->ri_pd, qp_init_attr); if (err) goto out_destroy;

@@ -698,25 +698,27 @@ rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) struct rpcrdma_xprt *r_xprt = container_of(ia, struct rpcrdma_xprt, rx_ia); struct rpc_xprt *xprt = &r_xprt->rx_xprt; + struct ib_qp_init_attr qp_init_attr; int rc;

retry: + memcpy(&qp_init_attr, &ep->rep_attr, sizeof(qp_init_attr)); switch (ep->rep_connected) { case 0: dprintk("RPC: %s: connecting...\n", __func__); - rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr); + rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &qp_init_attr); if (rc) { rc = -ENETUNREACH; goto out_noupdate; } break; case -ENODEV: - rc = rpcrdma_ep_recreate_xprt(r_xprt, ep, ia); + rc = rpcrdma_ep_recreate_xprt(r_xprt, &qp_init_attr); if (rc) goto out_noupdate; break; default: - rc = rpcrdma_ep_reconnect(r_xprt, ep, ia); + rc = rpcrdma_ep_reconnect(r_xprt, &qp_init_attr); if (rc) goto out; }

From: Chengguang Xu cgxu519@zoho.com.cn

[ Upstream commit c87a37ebd40b889178664c2c09cc187334146292 ]

Currently on mmap cache policy, we always attach writeback_fid whether mmap type is SHARED or PRIVATE. However, in the use case of kata-container which combines 9p(Guest OS) with overlayfs(Host OS), this behavior will trigger overlayfs' copy-up when excute command inside container.

Link: http://lkml.kernel.org/r/20190820100325.10313-1-cgxu519@zoho.com.cn Signed-off-by: Chengguang Xu cgxu519@zoho.com.cn Signed-off-by: Dominique Martinet dominique.martinet@cea.fr Signed-off-by: Sasha Levin sashal@kernel.org --- fs/9p/vfs_file.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 4cc966a31cb37..fe7f0bd2048e4 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -513,6 +513,7 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma) v9inode = V9FS_I(inode); mutex_lock(&v9inode->v_mutex); if (!v9inode->writeback_fid && + (vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) { /* * clone a fid and add it to writeback_fid @@ -614,6 +615,8 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma) (vma->vm_end - vma->vm_start - 1), };

+ if (!(vma->vm_flags & VM_SHARED)) + return;

p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma);

From: Igor Druzhinin igor.druzhinin@citrix.com

[ Upstream commit a4098bc6eed5e31e0391bcc068e61804c98138df ]

If MCFG area is not reserved in E820, Xen by default will defer its usage until Dom0 registers it explicitly after ACPI parser recognizes it as a reserved resource in DSDT. Having it reserved in E820 is not mandatory according to "PCI Firmware Specification, rev 3.2" (par. 4.1.2) and firmware is free to keep a hole in E820 in that place. Xen doesn't know what exactly is inside this hole since it lacks full ACPI view of the platform therefore it's potentially harmful to access MCFG region without additional checks as some machines are known to provide inconsistent information on the size of the region.

Now xen_mcfg_late() runs after acpi_init() which is too late as some basic PCI enumeration starts exactly there as well. Trying to register a device prior to MCFG reservation causes multiple problems with PCIe extended capability initializations in Xen (e.g. SR-IOV VF BAR sizing). There are no convenient hooks for us to subscribe to so register MCFG areas earlier upon the first invocation of xen_add_device(). It should be safe to do once since all the boot time buses must have their MCFG areas in MCFG table already and we don't support PCI bus hot-plug.

Signed-off-by: Igor Druzhinin igor.druzhinin@citrix.com Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/xen/pci.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index 3eeb9bea76300..224df03ce42e3 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -17,6 +17,8 @@ #include "../pci/pci.h" #ifdef CONFIG_PCI_MMCONFIG #include <asm/pci_x86.h> + +static int xen_mcfg_late(void); #endif

static bool __read_mostly pci_seg_supported = true; @@ -28,7 +30,18 @@ static int xen_add_device(struct device *dev) #ifdef CONFIG_PCI_IOV struct pci_dev *physfn = pci_dev->physfn; #endif - +#ifdef CONFIG_PCI_MMCONFIG + static bool pci_mcfg_reserved = false; + /* + * Reserve MCFG areas in Xen on first invocation due to this being + * potentially called from inside of acpi_init immediately after + * MCFG table has been finally parsed. + */ + if (!pci_mcfg_reserved) { + xen_mcfg_late(); + pci_mcfg_reserved = true; + } +#endif if (pci_seg_supported) { struct { struct physdev_pci_device_add add; @@ -201,7 +214,7 @@ static int __init register_xen_pci_notifier(void) arch_initcall(register_xen_pci_notifier);

#ifdef CONFIG_PCI_MMCONFIG -static int __init xen_mcfg_late(void) +static int xen_mcfg_late(void) { struct pci_mmcfg_region *cfg; int rc; @@ -240,8 +253,4 @@ static int __init xen_mcfg_late(void) } return 0; } -/* - * Needs to be done after acpi_init which are subsys_initcall. - */ -subsys_initcall_sync(xen_mcfg_late); #endif

From: Luis Henriques lhenriques@suse.com

[ Upstream commit 750670341a24cb714e624e0fd7da30900ad93752 ]

When filling an inode with info from the MDS, i_blkbits is being initialized using fl_stripe_unit, which contains the stripe unit in bytes. Unfortunately, this doesn't make sense for directories as they have fl_stripe_unit set to '0'. This means that i_blkbits will be set to 0xff, causing an UBSAN undefined behaviour in i_blocksize():

UBSAN: Undefined behaviour in ./include/linux/fs.h:731:12 shift exponent 255 is too large for 32-bit type 'int'

Fix this by initializing i_blkbits to CEPH_BLOCK_SHIFT if fl_stripe_unit is zero.

Signed-off-by: Luis Henriques lhenriques@suse.com Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/inode.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 18500edefc56f..3b537e7038c7a 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -801,7 +801,12 @@ static int fill_inode(struct inode *inode, struct page *locked_page,

/* update inode */ inode->i_rdev = le32_to_cpu(info->rdev); - inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1; + /* directories have fl_stripe_unit set to zero */ + if (le32_to_cpu(info->layout.fl_stripe_unit)) + inode->i_blkbits = + fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1; + else + inode->i_blkbits = CEPH_BLOCK_SHIFT;

__ceph_update_quota(ci, iinfo->max_bytes, iinfo->max_files);

From: Erqi Chen chenerqi@gmail.com

[ Upstream commit 71a228bc8d65900179e37ac309e678f8c523f133 ]

If client mds session is evicted in CEPH_MDS_SESSION_OPENING state, mds won't send session msg to client, and delayed_work skip CEPH_MDS_SESSION_OPENING state session, the session hang forever.

Allow ceph_con_keepalive to reconnect a session in OPENING to avoid session hang. Also, ensure that we skip sessions in RESTARTING and REJECTED states since those states can't be resurrected by issuing a keepalive.

Link: https://tracker.ceph.com/issues/41551 Signed-off-by: Erqi Chen chenerqi@gmail.com Reviewed-by: "Yan, Zheng" zyan@redhat.com Signed-off-by: Jeff Layton jlayton@kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/mds_client.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 920e9f048bd8f..b11af7d8e8e93 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4044,7 +4044,9 @@ static void delayed_work(struct work_struct *work) pr_info("mds%d hung\n", s->s_mds); } } - if (s->s_state < CEPH_MDS_SESSION_OPEN) { + if (s->s_state == CEPH_MDS_SESSION_NEW || + s->s_state == CEPH_MDS_SESSION_RESTARTING || + s->s_state == CEPH_MDS_SESSION_REJECTED) { /* this mds is failed or recovering, just wait */ ceph_put_mds_session(s); continue;

From: Ryan Chen ryan_chen@aspeedtech.com

[ Upstream commit b3528b4874480818e38e4da019d655413c233e6a ]

The ast2600 can be supported by the same code as the ast2500.

Signed-off-by: Ryan Chen ryan_chen@aspeedtech.com Signed-off-by: Joel Stanley joel@jms.id.au Reviewed-by: Guenter Roeck linux@roeck-us.net Link: https://lore.kernel.org/r/20190819051738.17370-3-joel@jms.id.au Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Wim Van Sebroeck wim@linux-watchdog.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/watchdog/aspeed_wdt.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c index cc71861e033a5..5b64bc2e87888 100644 --- a/drivers/watchdog/aspeed_wdt.c +++ b/drivers/watchdog/aspeed_wdt.c @@ -34,6 +34,7 @@ static const struct aspeed_wdt_config ast2500_config = { static const struct of_device_id aspeed_wdt_of_table[] = { { .compatible = "aspeed,ast2400-wdt", .data = &ast2400_config }, { .compatible = "aspeed,ast2500-wdt", .data = &ast2500_config }, + { .compatible = "aspeed,ast2600-wdt", .data = &ast2500_config }, { }, }; MODULE_DEVICE_TABLE(of, aspeed_wdt_of_table); @@ -259,7 +260,8 @@ static int aspeed_wdt_probe(struct platform_device *pdev) set_bit(WDOG_HW_RUNNING, &wdt->wdd.status); }

- if (of_device_is_compatible(np, "aspeed,ast2500-wdt")) { + if ((of_device_is_compatible(np, "aspeed,ast2500-wdt")) || + (of_device_is_compatible(np, "aspeed,ast2600-wdt"))) { u32 reg = readl(wdt->base + WDT_RESET_WIDTH);

reg &= config->ext_pulse_width_mask;

From: Felix Kuehling Felix.Kuehling@amd.com

[ Upstream commit dcafbd50f2e4d5cc964aae409fb5691b743fba23 ]

Hawaii needs to flush caches explicitly, submitting an IB in a user VMID from kernel mode. There is no s_fence in this case.

Fixes: eb3961a57424 ("drm/amdgpu: remove fence context from the job") Signed-off-by: Felix Kuehling Felix.Kuehling@amd.com Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 7850084a05e3a..60655834d6498 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -143,7 +143,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, /* ring tests don't use a job */ if (job) { vm = job->vm; - fence_ctx = job->base.s_fence->scheduled.context; + fence_ctx = job->base.s_fence ? + job->base.s_fence->scheduled.context : 0; } else { vm = NULL; fence_ctx = 0;

From: Masami Hiramatsu mhiramat@kernel.org

[ Upstream commit 9e6124d9d635957b56717f85219a88701617253f ]

Since add_probe_trace_event() can reuse tf->tevs[i] after calling clear_probe_trace_event(), this can make perf-probe crash if the 1st attempt of probe event finding fails to find an event argument, and the 2nd attempt fails to find probe point.

E.g. $ perf probe -D "task_pid_nr tsk" Failed to find 'tsk' in this function. Failed to get entry address of warn_bad_vsyscall Segmentation fault (core dumped)

Committer testing:

After the patch:

$ perf probe -D "task_pid_nr tsk" Failed to find 'tsk' in this function. Failed to get entry address of warn_bad_vsyscall Failed to get entry address of signal_fault Failed to get entry address of show_signal Failed to get entry address of umip_printk Failed to get entry address of __bad_area_nosemaphore <SNIP> Failed to get entry address of sock_set_timeout Failed to get entry address of tcp_recvmsg Probe point 'task_pid_nr' not found. Error: Failed to add events. $

Fixes: 092b1f0b5f9f ("perf probe: Clear probe_trace_event when add_probe_trace_event() fails") Signed-off-by: Masami Hiramatsu mhiramat@kernel.org Tested-by: Arnaldo Carvalho de Melo acme@redhat.com Cc: Jiri Olsa jolsa@redhat.com Cc: Namhyung Kim namhyung@kernel.org Cc: Wang Nan wangnan0@huawei.com Link: http://lore.kernel.org/lkml/156856587999.25775.5145779959474477595.stgit@dev... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/probe-event.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 8394d48f8b32e..3355c445abedf 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2329,6 +2329,7 @@ void clear_probe_trace_event(struct probe_trace_event *tev) } } zfree(&tev->args); + tev->nargs = 0; }

struct kprobe_blacklist_node {

From: Trond Myklebust trondmy@gmail.com

[ Upstream commit 9ba828861c56a21d211d5d10f5643774b1ea330d ]

If the copy of the RPC reply into our buffers did not complete, and we could end up with a truncated message. In that case, just resend the call.

Fixes: a0584ee9aed80 ("SUNRPC: Use struct xdr_stream when decoding...") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sunrpc/clnt.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 76e745ff78138..d8136b829804f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2479,6 +2479,7 @@ call_decode(struct rpc_task *task) struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; struct xdr_stream xdr; + int err;

dprint_status(task);

@@ -2501,6 +2502,15 @@ call_decode(struct rpc_task *task) * before it changed req->rq_reply_bytes_recvd. */ smp_rmb(); + + /* + * Did we ever call xprt_complete_rqst()? If not, we should assume + * the message is incomplete. + */ + err = -EAGAIN; + if (!req->rq_reply_bytes_recvd) + goto out; + req->rq_rcv_buf.len = req->rq_private_buf.len;

/* Check that the softirq receive buffer is valid */ @@ -2509,7 +2519,9 @@ call_decode(struct rpc_task *task)

xdr_init_decode(&xdr, &req->rq_rcv_buf, req->rq_rcv_buf.head[0].iov_base, req); - switch (rpc_decode_header(task, &xdr)) { + err = rpc_decode_header(task, &xdr); +out: + switch (err) { case 0: task->tk_action = rpc_exit_task; task->tk_status = rpcauth_unwrap_resp(task, &xdr);

From: Fabrice Gasnier fabrice.gasnier@st.com

[ Upstream commit c91e3234c6035baf5a79763cb4fcd5d23ce75c2b ]

LPTimer can use a 32KHz clock for counting. It depends on clock tree configuration. In such a case, PWM output frequency range is limited. Although unlikely, nothing prevents user from requesting a PWM frequency above counting clock (32KHz for instance): - This causes (prd - 1) = 0xffff to be written in ARR register later in the apply() routine. This results in badly configured PWM period (and also duty_cycle). Add a check to report an error is such a case.

Signed-off-by: Fabrice Gasnier fabrice.gasnier@st.com Reviewed-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Thierry Reding thierry.reding@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pwm/pwm-stm32-lp.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c index 2211a642066db..97a9afa191ee0 100644 --- a/drivers/pwm/pwm-stm32-lp.c +++ b/drivers/pwm/pwm-stm32-lp.c @@ -59,6 +59,12 @@ static int stm32_pwm_lp_apply(struct pwm_chip *chip, struct pwm_device *pwm, /* Calculate the period and prescaler value */ div = (unsigned long long)clk_get_rate(priv->clk) * state->period; do_div(div, NSEC_PER_SEC); + if (!div) { + /* Clock is too slow to achieve requested period. */ + dev_dbg(priv->chip.dev, "Can't reach %u ns\n", state->period); + return -EINVAL; + } + prd = div; while (div > STM32_LPTIM_MAX_ARR) { presc++;

From: Bjørn Mork bjorn@mork.no

[ Upstream commit 8d3d7c2029c1b360f1a6b0a2fca470b57eb575c0 ]

Endpoints with zero wMaxPacketSize are not usable for transferring data. Ignore such endpoints when looking for valid in, out and status pipes, to make the drivers more robust against invalid and meaningless descriptors.

The wMaxPacketSize of these endpoints are used for memory allocations and as divisors in many usbnet minidrivers. Avoiding zero is therefore critical.

Signed-off-by: Bjørn Mork bjorn@mork.no Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/usbnet.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 72514c46b4786..07c00e378a5cd 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -100,6 +100,11 @@ int usbnet_get_endpoints(struct usbnet *dev, struct usb_interface *intf) int intr = 0;

e = alt->endpoint + ep; + + /* ignore endpoints which cannot transfer data */ + if (!usb_endpoint_maxp(&e->desc)) + continue; + switch (e->desc.bmAttributes) { case USB_ENDPOINT_XFER_INT: if (!usb_endpoint_dir_in(&e->desc))

From: Cong Wang xiyou.wangcong@gmail.com

[ Upstream commit 62794fc4fbf52f2209dc094ea255eaef760e7d01 ]

The TCA_KIND attribute is of NLA_STRING which does not check the NUL char. KMSAN reported an uninit-value of TCA_KIND which is likely caused by the lack of NUL.

Change it to NLA_NUL_STRING and add a max len too.

Fixes: 8b4c3cdd9dd8 ("net: sched: Add policy validation for tc attributes") Reported-and-tested-by: syzbot+618aacd49e8c8b8486bd@syzkaller.appspotmail.com Cc: Jamal Hadi Salim jhs@mojatatu.com Signed-off-by: Cong Wang xiyou.wangcong@gmail.com Reviewed-by: David Ahern dsahern@gmail.com Acked-by: Jiri Pirko jiri@mellanox.com Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_api.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1047825d9f48d..81d58b2806122 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1390,7 +1390,8 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) }

const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { - [TCA_KIND] = { .type = NLA_STRING }, + [TCA_KIND] = { .type = NLA_NUL_STRING, + .len = IFNAMSIZ - 1 }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED },

From: Arvind Sankar nivedita@alum.mit.edu

[ Upstream commit ca14c996afe7228ff9b480cf225211cc17212688 ]

Since commit:

b059f801a937 ("x86/purgatory: Use CFLAGS_REMOVE rather than reset KBUILD_CFLAGS")

kexec breaks if GCC_PLUGIN_STACKLEAK=y is enabled, as the purgatory contains undefined references to stackleak_track_stack.

Attempting to load a kexec kernel results in this failure:

kexec: Undefined symbol: stackleak_track_stack kexec-bzImage64: Loading purgatory failed

Fix this by disabling the stackleak plugin for the purgatory.

Signed-off-by: Arvind Sankar nivedita@alum.mit.edu Reviewed-by: Nick Desaulniers ndesaulniers@google.com Cc: Borislav Petkov bp@alien8.de Cc: H. Peter Anvin hpa@zytor.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Fixes: b059f801a937 ("x86/purgatory: Use CFLAGS_REMOVE rather than reset KBUILD_CFLAGS") Link: https://lkml.kernel.org/r/20190923171753.GA2252517@rani.riverdale.lan Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/purgatory/Makefile | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 10fb42da0007e..b81b5172cf994 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -23,6 +23,7 @@ KCOV_INSTRUMENT := n

PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss +PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN)

# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That # in turn leaves some undefined symbols like __fentry__ in purgatory and not

From: Ido Schimmel idosch@mellanox.com

[ Upstream commit 1851799e1d2978f68eea5d9dff322e121dcf59c1 ]

thermal_zone_device_unregister() cancels the delayed work that polls the thermal zone, but it does not wait for it to finish. This is racy with respect to the freeing of the thermal zone device, which can result in a use-after-free [1].

Fix this by waiting for the delayed work to finish before freeing the thermal zone device. Note that thermal_zone_device_set_polling() is never invoked from an atomic context, so it is safe to call cancel_delayed_work_sync() that can block.

[1] [ +0.002221] ================================================================== [ +0.000064] BUG: KASAN: use-after-free in __mutex_lock+0x1076/0x11c0 [ +0.000016] Read of size 8 at addr ffff8881e48e0450 by task kworker/1:0/17

[ +0.000023] CPU: 1 PID: 17 Comm: kworker/1:0 Not tainted 5.2.0-rc6-custom-02495-g8e73ca3be4af #1701 [ +0.000010] Hardware name: Mellanox Technologies Ltd. MSN2100-CB2FO/SA001017, BIOS 5.6.5 06/07/2016 [ +0.000016] Workqueue: events_freezable_power_ thermal_zone_device_check [ +0.000012] Call Trace: [ +0.000021] dump_stack+0xa9/0x10e [ +0.000020] print_address_description.cold.2+0x9/0x25e [ +0.000018] __kasan_report.cold.3+0x78/0x9d [ +0.000016] kasan_report+0xe/0x20 [ +0.000016] __mutex_lock+0x1076/0x11c0 [ +0.000014] step_wise_throttle+0x72/0x150 [ +0.000018] handle_thermal_trip+0x167/0x760 [ +0.000019] thermal_zone_device_update+0x19e/0x5f0 [ +0.000019] process_one_work+0x969/0x16f0 [ +0.000017] worker_thread+0x91/0xc40 [ +0.000014] kthread+0x33d/0x400 [ +0.000015] ret_from_fork+0x3a/0x50

[ +0.000020] Allocated by task 1: [ +0.000015] save_stack+0x19/0x80 [ +0.000015] __kasan_kmalloc.constprop.4+0xc1/0xd0 [ +0.000014] kmem_cache_alloc_trace+0x152/0x320 [ +0.000015] thermal_zone_device_register+0x1b4/0x13a0 [ +0.000015] mlxsw_thermal_init+0xc92/0x23d0 [ +0.000014] __mlxsw_core_bus_device_register+0x659/0x11b0 [ +0.000013] mlxsw_core_bus_device_register+0x3d/0x90 [ +0.000013] mlxsw_pci_probe+0x355/0x4b0 [ +0.000014] local_pci_probe+0xc3/0x150 [ +0.000013] pci_device_probe+0x280/0x410 [ +0.000013] really_probe+0x26a/0xbb0 [ +0.000013] driver_probe_device+0x208/0x2e0 [ +0.000013] device_driver_attach+0xfe/0x140 [ +0.000013] __driver_attach+0x110/0x310 [ +0.000013] bus_for_each_dev+0x14b/0x1d0 [ +0.000013] driver_register+0x1c0/0x400 [ +0.000015] mlxsw_sp_module_init+0x5d/0xd3 [ +0.000014] do_one_initcall+0x239/0x4dd [ +0.000013] kernel_init_freeable+0x42b/0x4e8 [ +0.000012] kernel_init+0x11/0x18b [ +0.000013] ret_from_fork+0x3a/0x50

[ +0.000015] Freed by task 581: [ +0.000013] save_stack+0x19/0x80 [ +0.000014] __kasan_slab_free+0x125/0x170 [ +0.000013] kfree+0xf3/0x310 [ +0.000013] thermal_release+0xc7/0xf0 [ +0.000014] device_release+0x77/0x200 [ +0.000014] kobject_put+0x1a8/0x4c0 [ +0.000014] device_unregister+0x38/0xc0 [ +0.000014] thermal_zone_device_unregister+0x54e/0x6a0 [ +0.000014] mlxsw_thermal_fini+0x184/0x35a [ +0.000014] mlxsw_core_bus_device_unregister+0x10a/0x640 [ +0.000013] mlxsw_devlink_core_bus_device_reload+0x92/0x210 [ +0.000015] devlink_nl_cmd_reload+0x113/0x1f0 [ +0.000014] genl_family_rcv_msg+0x700/0xee0 [ +0.000013] genl_rcv_msg+0xca/0x170 [ +0.000013] netlink_rcv_skb+0x137/0x3a0 [ +0.000012] genl_rcv+0x29/0x40 [ +0.000013] netlink_unicast+0x49b/0x660 [ +0.000013] netlink_sendmsg+0x755/0xc90 [ +0.000013] __sys_sendto+0x3de/0x430 [ +0.000013] __x64_sys_sendto+0xe2/0x1b0 [ +0.000013] do_syscall_64+0xa4/0x4d0 [ +0.000013] entry_SYSCALL_64_after_hwframe+0x49/0xbe

[ +0.000017] The buggy address belongs to the object at ffff8881e48e0008 which belongs to the cache kmalloc-2k of size 2048 [ +0.000012] The buggy address is located 1096 bytes inside of 2048-byte region [ffff8881e48e0008, ffff8881e48e0808) [ +0.000007] The buggy address belongs to the page: [ +0.000012] page:ffffea0007923800 refcount:1 mapcount:0 mapping:ffff88823680d0c0 index:0x0 compound_mapcount: 0 [ +0.000020] flags: 0x200000000010200(slab|head) [ +0.000019] raw: 0200000000010200 ffffea0007682008 ffffea00076ab808 ffff88823680d0c0 [ +0.000016] raw: 0000000000000000 00000000000d000d 00000001ffffffff 0000000000000000 [ +0.000007] page dumped because: kasan: bad access detected

[ +0.000012] Memory state around the buggy address: [ +0.000012] ffff8881e48e0300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000012] ffff8881e48e0380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000012] >ffff8881e48e0400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000008] ^ [ +0.000012] ffff8881e48e0480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000012] ffff8881e48e0500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ +0.000007] ==================================================================

Fixes: b1569e99c795 ("ACPI: move thermal trip handling to generic thermal layer") Reported-by: Jiri Pirko jiri@mellanox.com Signed-off-by: Ido Schimmel idosch@mellanox.com Acked-by: Jiri Pirko jiri@mellanox.com Signed-off-by: Zhang Rui rui.zhang@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/thermal/thermal_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 6bab66e84eb58..ebe15f2cf7fc3 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -304,7 +304,7 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz, &tz->poll_queue, msecs_to_jiffies(delay)); else - cancel_delayed_work(&tz->poll_queue); + cancel_delayed_work_sync(&tz->poll_queue); }

static void monitor_thermal_zone(struct thermal_zone_device *tz)

From: Andrei Dulea adulea@amazon.de

[ Upstream commit 6ccb72f8374e17d60b58a7bfd5570496332c54e2 ]

Downgrading an existing large mapping to a mapping using smaller page-sizes works only for the mappings created with page-mode 7 (i.e. non-default page size).

Treat large mappings created with page-mode 0 (i.e. default page size) like a non-present mapping and allow to overwrite it in alloc_pte().

While around, make sure that we flush the TLB only if we change an existing mapping, otherwise we might end up acting on garbage PTEs.

Fixes: 6d568ef9a622 ("iommu/amd: Allow downgrading page-sizes in alloc_pte()") Signed-off-by: Andrei Dulea adulea@amazon.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/amd_iommu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 61de81965c44e..0fb42a846404b 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1490,6 +1490,7 @@ static u64 *alloc_pte(struct protection_domain *domain, pte_level = PM_PTE_LEVEL(__pte);

if (!IOMMU_PTE_PRESENT(__pte) || + pte_level == PAGE_MODE_NONE || pte_level == PAGE_MODE_7_LEVEL) { page = (u64 *)get_zeroed_page(gfp); if (!page) @@ -1500,7 +1501,7 @@ static u64 *alloc_pte(struct protection_domain *domain, /* pte could have been changed somewhere. */ if (cmpxchg64(pte, __pte, __npte) != __pte) free_page((unsigned long)page); - else if (pte_level == PAGE_MODE_7_LEVEL) + else if (IOMMU_PTE_PRESENT(__pte)) domain->updated = true;

continue;

From: Dmytro Linkin dmitrolin@mellanox.com

[ Upstream commit fe1587a7de94912ed75ba5ddbfabf0741f9f8239 ]

In mlx5 parse_tunnel_attr() function dispatch on encap IP address type is performed by directly checking flow_rule_match_key() on FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, and then on FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS. However, since those are stored in union, first check is always true if any type of encap address is set, which leads to IPv6 tunnel encap address being parsed as IPv4 by mlx5. Determine correct IP address type by checking control key first and if it set, take address type from match.key->addr_type.

Fixes: d1bda7eecd88 ("net/mlx5e: Allow matching only enc_key_id/enc_dst_port for decapsulation action") Signed-off-by: Dmytro Linkin dmitrolin@mellanox.com Reviewed-by: Vlad Buslov vladbu@mellanox.com Reviewed-by: Eli Britstein elibr@mellanox.com Reviewed-by: Roi Dayan roid@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 89 +++++++++++-------- 1 file changed, 53 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 00b2d4a86159f..98be5fe336743 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1369,46 +1369,63 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, return err; }

- if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { - struct flow_match_ipv4_addrs match; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + struct flow_match_control match; + u16 addr_type;

- flow_rule_match_enc_ipv4_addrs(rule, &match); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, - src_ipv4_src_ipv6.ipv4_layout.ipv4, - ntohl(match.mask->src)); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, - src_ipv4_src_ipv6.ipv4_layout.ipv4, - ntohl(match.key->src)); - - MLX5_SET(fte_match_set_lyr_2_4, headers_c, - dst_ipv4_dst_ipv6.ipv4_layout.ipv4, - ntohl(match.mask->dst)); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, - dst_ipv4_dst_ipv6.ipv4_layout.ipv4, - ntohl(match.key->dst)); - - MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP); - } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { - struct flow_match_ipv6_addrs match; + flow_rule_match_enc_control(rule, &match); + addr_type = match.key->addr_type;

- flow_rule_match_enc_ipv6_addrs(rule, &match); - memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, - src_ipv4_src_ipv6.ipv6_layout.ipv6), - &match.mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); - memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, - src_ipv4_src_ipv6.ipv6_layout.ipv6), - &match.key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + /* For tunnel addr_type used same key id`s as for non-tunnel */ + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_match_ipv4_addrs match;

- memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, - dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &match.mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); - memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, - dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &match.key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + flow_rule_match_enc_ipv4_addrs(rule, &match); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + src_ipv4_src_ipv6.ipv4_layout.ipv4, + ntohl(match.mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + src_ipv4_src_ipv6.ipv4_layout.ipv4, + ntohl(match.key->src));

- MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + dst_ipv4_dst_ipv6.ipv4_layout.ipv4, + ntohl(match.mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + dst_ipv4_dst_ipv6.ipv4_layout.ipv4, + ntohl(match.key->dst)); + + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, + ethertype); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, + ETH_P_IP); + } else if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_match_ipv6_addrs match; + + flow_rule_match_enc_ipv6_addrs(rule, &match); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + &match.mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, + ipv6)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + &match.key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, + ipv6)); + + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + &match.mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, + ipv6)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + &match.key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, + ipv6)); + + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, + ethertype); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, + ETH_P_IPV6); + } }

if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) {

From: Wanpeng Li wanpengli@tencent.com

[ Upstream commit a073d7e3ad687a7ef32b65affe80faa7ce89bf92 ]

Reported by syzkaller:

kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN RIP: 0010:__apic_accept_irq+0x46/0x740 arch/x86/kvm/lapic.c:1029 Call Trace: kvm_apic_set_irq+0xb4/0x140 arch/x86/kvm/lapic.c:558 stimer_notify_direct arch/x86/kvm/hyperv.c:648 [inline] stimer_expiration arch/x86/kvm/hyperv.c:659 [inline] kvm_hv_process_stimers+0x594/0x1650 arch/x86/kvm/hyperv.c:686 vcpu_enter_guest+0x2b2a/0x54b0 arch/x86/kvm/x86.c:7896 vcpu_run+0x393/0xd40 arch/x86/kvm/x86.c:8152 kvm_arch_vcpu_ioctl_run+0x636/0x900 arch/x86/kvm/x86.c:8360 kvm_vcpu_ioctl+0x6cf/0xaf0 arch/x86/kvm/../../../virt/kvm/kvm_main.c:2765

The testcase programs HV_X64_MSR_STIMERn_CONFIG/HV_X64_MSR_STIMERn_COUNT, in addition, there is no lapic in the kernel, the counters value are small enough in order that kvm_hv_process_stimers() inject this already-expired timer interrupt into the guest through lapic in the kernel which triggers the NULL deferencing. This patch fixes it by don't advertise direct mode synthetic timers and discarding the inject when lapic is not in kernel.

syzkaller source: https://syzkaller.appspot.com/x/repro.c?x=1752fe0a600000

Reported-by: syzbot+dff25ee91f0c7d5c1695@syzkaller.appspotmail.com Cc: Paolo Bonzini pbonzini@redhat.com Cc: Radim Krčmář rkrcmar@redhat.com Signed-off-by: Wanpeng Li wanpengli@tencent.com Reviewed-by: Vitaly Kuznetsov vkuznets@redhat.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/hyperv.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index fff790a3f4ee9..c0867b0aae3ec 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -645,7 +645,9 @@ static int stimer_notify_direct(struct kvm_vcpu_hv_stimer *stimer) .vector = stimer->config.apic_vector };

- return !kvm_apic_set_irq(vcpu, &irq, NULL); + if (lapic_in_kernel(vcpu)) + return !kvm_apic_set_irq(vcpu, &irq, NULL); + return 0; }

static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer) @@ -1852,7 +1854,13 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,

ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; - ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + + /* + * Direct Synthetic timers only make sense with in-kernel + * LAPIC + */ + if (lapic_in_kernel(vcpu)) + ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE;

break;

From: zhengbin zhengbin13@huawei.com

[ Upstream commit 9ad09b1976c562061636ff1e01bfc3a57aebe56b ]

If cuse_send_init fails, need to fuse_conn_put cc->fc.

cuse_channel_open->fuse_conn_init->refcount_set(&fc->count, 1) ->fuse_dev_alloc->fuse_conn_get ->fuse_dev_free->fuse_conn_put

Fixes: cc080e9e9be1 ("fuse: introduce per-instance fuse_dev structure") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: zhengbin zhengbin13@huawei.com Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/fuse/cuse.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index bab7a0db81dd4..f3b7208846506 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -519,6 +519,7 @@ static int cuse_channel_open(struct inode *inode, struct file *file) rc = cuse_send_init(cc); if (rc) { fuse_dev_free(fud); + fuse_conn_put(&cc->fc); return rc; } file->private_data = fud;

From: Nathan Chancellor natechancellor@gmail.com

[ Upstream commit 59f08896f058a92f03a0041b397a1a227c5e8529 ]

After commit 62974fc389b3 ("libnvdimm: Enable unit test infrastructure compile checks"), clang warns:

In file included from ../drivers/nvdimm/../../tools/testing/nvdimm/test/iomap.c:15: ../drivers/nvdimm/../../tools/testing/nvdimm/test/nfit_test.h:206:15: warning: redefinition of typedef 'acpi_handle' is a C11 feature [-Wtypedef-redefinition] typedef void *acpi_handle; ^ ../include/acpi/actypes.h:424:15: note: previous definition is here typedef void *acpi_handle; /* Actually a ptr to a NS Node */ ^ 1 warning generated.

The include chain:

iomap.c -> linux/acpi.h -> acpi/acpi.h -> acpi/actypes.h nfit_test.h

Avoid this by including linux/acpi.h in nfit_test.h, which allows us to remove both the typedef and the forward declaration of acpi_object.

Link: https://github.com/ClangBuiltLinux/linux/issues/660 Signed-off-by: Nathan Chancellor natechancellor@gmail.com Reviewed-by: Ira Weiny ira.weiny@intel.com Link: https://lore.kernel.org/r/20190918042148.77553-1-natechancellor@gmail.com Signed-off-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/nvdimm/test/nfit_test.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index 448d686da8b13..0bf5640f1f071 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -4,6 +4,7 @@ */ #ifndef __NFIT_TEST_H__ #define __NFIT_TEST_H__ +#include <linux/acpi.h> #include <linux/list.h> #include <linux/uuid.h> #include <linux/ioport.h> @@ -202,9 +203,6 @@ struct nd_intel_lss { __u32 status; } __packed;

-union acpi_object; -typedef void *acpi_handle; - typedef struct nfit_test_resource *(*nfit_test_lookup_fn)(resource_size_t); typedef union acpi_object *(*nfit_test_evaluate_dsm_fn)(acpi_handle handle, const guid_t *guid, u64 rev, u64 func,

From: Mathieu Desnoyers mathieu.desnoyers@efficios.com

[ Upstream commit 2840cf02fae627860156737e83326df354ee4ec6 ]

When the prev and next task's mm change, switch_mm() provides the core serializing guarantees before returning to usermode. The only case where an explicit core serialization is needed is when the scheduler keeps the same mm for prev and next.

Suggested-by: Oleg Nesterov oleg@redhat.com Signed-off-by: Mathieu Desnoyers mathieu.desnoyers@efficios.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Chris Metcalf cmetcalf@ezchip.com Cc: Christoph Lameter cl@linux.com Cc: Eric W. Biederman ebiederm@xmission.com Cc: Kirill Tkhai tkhai@yandex.ru Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Mike Galbraith efault@gmx.de Cc: Paul E. McKenney paulmck@linux.ibm.com Cc: Peter Zijlstra peterz@infradead.org Cc: Russell King - ARM Linux admin linux@armlinux.org.uk Cc: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/20190919173705.2181-4-mathieu.desnoyers@efficios.c... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/sched/mm.h | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 4a7944078cc35..8557ec6642130 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -362,6 +362,8 @@ enum {

static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { + if (current->mm != mm) + return; if (likely(!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE))) return;

From: KeMeng Shi shikemeng@huawei.com

[ Upstream commit 714e501e16cd473538b609b3e351b2cc9f7f09ed ]

An oops can be triggered in the scheduler when running qemu on arm64:

Unable to handle kernel paging request at virtual address ffff000008effe40 Internal error: Oops: 96000007 [#1] SMP Process migration/0 (pid: 12, stack limit = 0x00000000084e3736) pstate: 20000085 (nzCv daIf -PAN -UAO) pc : __ll_sc___cmpxchg_case_acq_4+0x4/0x20 lr : move_queued_task.isra.21+0x124/0x298 ... Call trace: __ll_sc___cmpxchg_case_acq_4+0x4/0x20 __migrate_task+0xc8/0xe0 migration_cpu_stop+0x170/0x180 cpu_stopper_thread+0xec/0x178 smpboot_thread_fn+0x1ac/0x1e8 kthread+0x134/0x138 ret_from_fork+0x10/0x18

__set_cpus_allowed_ptr() will choose an active dest_cpu in affinity mask to migrage the process if process is not currently running on any one of the CPUs specified in affinity mask. __set_cpus_allowed_ptr() will choose an invalid dest_cpu (dest_cpu >= nr_cpu_ids, 1024 in my virtual machine) if CPUS in an affinity mask are deactived by cpu_down after cpumask_intersects check. cpumask_test_cpu() of dest_cpu afterwards is overflown and may pass if corresponding bit is coincidentally set. As a consequence, kernel will access an invalid rq address associate with the invalid CPU in migration_cpu_stop->__migrate_task->move_queued_task and the Oops occurs.

The reproduce the crash:

1) A process repeatedly binds itself to cpu0 and cpu1 in turn by calling sched_setaffinity.

2) A shell script repeatedly does "echo 0 > /sys/devices/system/cpu/cpu1/online" and "echo 1 > /sys/devices/system/cpu/cpu1/online" in turn.

3) Oops appears if the invalid CPU is set in memory after tested cpumask.

Signed-off-by: KeMeng Shi shikemeng@huawei.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Valentin Schneider valentin.schneider@arm.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/1568616808-16808-1-git-send-email-shikemeng@huawei... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c index df9f1fe5689b0..7dc620dfd8baf 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1537,7 +1537,8 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, if (cpumask_equal(p->cpus_ptr, new_mask)) goto out;

- if (!cpumask_intersects(new_mask, cpu_valid_mask)) { + dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); + if (dest_cpu >= nr_cpu_ids) { ret = -EINVAL; goto out; } @@ -1558,7 +1559,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, if (cpumask_test_cpu(task_cpu(p), new_mask)) goto out;

- dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); if (task_running(rq, p) || p->state == TASK_WAKING) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */

From: Qian Cai cai@lca.pw

[ Upstream commit d1a445d3b86c9341ce7a0954c23be0edb5c9bec5 ]

There are many of those warnings.

In file included from ./arch/powerpc/include/asm/paca.h:15, from ./arch/powerpc/include/asm/current.h:13, from ./include/linux/thread_info.h:21, from ./include/asm-generic/preempt.h:5, from ./arch/powerpc/include/generated/asm/preempt.h:1, from ./include/linux/preempt.h:78, from ./include/linux/spinlock.h:51, from fs/fs-writeback.c:19: In function 'strncpy', inlined from 'perf_trace_writeback_page_template' at ./include/trace/events/writeback.h:56:1: ./include/linux/string.h:260:9: warning: '__builtin_strncpy' specified bound 32 equals destination size [-Wstringop-truncation] return __builtin_strncpy(p, q, size); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Fix it by using the new strscpy_pad() which was introduced in "lib/string: Add strscpy_pad() function" and will always be NUL-terminated instead of strncpy(). Also, change strlcpy() to use strscpy_pad() in this file for consistency.

Link: http://lkml.kernel.org/r/1564075099-27750-1-git-send-email-cai@lca.pw Fixes: 455b2864686d ("writeback: Initial tracing support") Fixes: 028c2dd184c0 ("writeback: Add tracing to balance_dirty_pages") Fixes: e84d0a4f8e39 ("writeback: trace event writeback_queue_io") Fixes: b48c104d2211 ("writeback: trace event bdi_dirty_ratelimit") Fixes: cc1676d917f3 ("writeback: Move requeueing when I_SYNC set to writeback_sb_inodes()") Fixes: 9fb0a7da0c52 ("writeback: add more tracepoints") Signed-off-by: Qian Cai cai@lca.pw Reviewed-by: Jan Kara jack@suse.cz Cc: Tobin C. Harding tobin@kernel.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Cc: Ingo Molnar mingo@redhat.com Cc: Tejun Heo tj@kernel.org Cc: Dave Chinner dchinner@redhat.com Cc: Fengguang Wu fengguang.wu@intel.com Cc: Jens Axboe axboe@kernel.dk Cc: Joe Perches joe@perches.com Cc: Kees Cook keescook@chromium.org Cc: Jann Horn jannh@google.com Cc: Jonathan Corbet corbet@lwn.net Cc: Nitin Gote nitin.r.gote@intel.com Cc: Rasmus Villemoes rasmus.villemoes@prevas.dk Cc: Stephen Kitt steve@sk2.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/trace/events/writeback.h | 38 +++++++++++++++++--------------- 1 file changed, 20 insertions(+), 18 deletions(-)

diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index aa7f3aeac7408..79095434c1be3 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -66,8 +66,9 @@ DECLARE_EVENT_CLASS(writeback_page_template, ),

TP_fast_assign( - strncpy(__entry->name, - mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", 32); + strscpy_pad(__entry->name, + mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", + 32); __entry->ino = mapping ? mapping->host->i_ino : 0; __entry->index = page->index; ), @@ -110,8 +111,8 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template, struct backing_dev_info *bdi = inode_to_bdi(inode);

/* may be called for files on pseudo FSes w/ unregistered bdi */ - strncpy(__entry->name, - bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32); + strscpy_pad(__entry->name, + bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; @@ -190,8 +191,8 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template, ),

TP_fast_assign( - strncpy(__entry->name, - dev_name(inode_to_bdi(inode)->dev), 32); + strscpy_pad(__entry->name, + dev_name(inode_to_bdi(inode)->dev), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); @@ -234,8 +235,9 @@ DECLARE_EVENT_CLASS(writeback_work_class, __field(unsigned int, cgroup_ino) ), TP_fast_assign( - strncpy(__entry->name, - wb->bdi->dev ? dev_name(wb->bdi->dev) : "(unknown)", 32); + strscpy_pad(__entry->name, + wb->bdi->dev ? dev_name(wb->bdi->dev) : + "(unknown)", 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; @@ -288,7 +290,7 @@ DECLARE_EVENT_CLASS(writeback_class, __field(unsigned int, cgroup_ino) ), TP_fast_assign( - strncpy(__entry->name, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%u", @@ -310,7 +312,7 @@ TRACE_EVENT(writeback_bdi_register, __array(char, name, 32) ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strscpy_pad(__entry->name, dev_name(bdi->dev), 32); ), TP_printk("bdi %s", __entry->name @@ -335,7 +337,7 @@ DECLARE_EVENT_CLASS(wbc_class, ),

TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strscpy_pad(__entry->name, dev_name(bdi->dev), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; @@ -386,7 +388,7 @@ TRACE_EVENT(writeback_queue_io, ), TP_fast_assign( unsigned long *older_than_this = work->older_than_this; - strncpy(__entry->name, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32); __entry->older = older_than_this ? *older_than_this : 0; __entry->age = older_than_this ? (jiffies - *older_than_this) * 1000 / HZ : -1; @@ -472,7 +474,7 @@ TRACE_EVENT(bdi_dirty_ratelimit, ),

TP_fast_assign( - strlcpy(__entry->bdi, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); @@ -537,7 +539,7 @@ TRACE_EVENT(balance_dirty_pages,

TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; - strlcpy(__entry->bdi, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32);

__entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + @@ -597,8 +599,8 @@ TRACE_EVENT(writeback_sb_inodes_requeue, ),

TP_fast_assign( - strncpy(__entry->name, - dev_name(inode_to_bdi(inode)->dev), 32); + strscpy_pad(__entry->name, + dev_name(inode_to_bdi(inode)->dev), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; @@ -671,8 +673,8 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, ),

TP_fast_assign( - strncpy(__entry->name, - dev_name(inode_to_bdi(inode)->dev), 32); + strscpy_pad(__entry->name, + dev_name(inode_to_bdi(inode)->dev), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when;

From: Valdis Kletnieks valdis.kletnieks@vt.edu

[ Upstream commit 0f74914071ab7e7b78731ed62bf350e3a344e0a5 ]

When building with W=1, gcc properly complains that there's no prototypes:

CC kernel/elfcore.o kernel/elfcore.c:7:17: warning: no previous prototype for 'elf_core_extra_phdrs' [-Wmissing-prototypes] 7 | Elf_Half __weak elf_core_extra_phdrs(void) | ^~~~~~~~~~~~~~~~~~~~ kernel/elfcore.c:12:12: warning: no previous prototype for 'elf_core_write_extra_phdrs' [-Wmissing-prototypes] 12 | int __weak elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ kernel/elfcore.c:17:12: warning: no previous prototype for 'elf_core_write_extra_data' [-Wmissing-prototypes] 17 | int __weak elf_core_write_extra_data(struct coredump_params *cprm) | ^~~~~~~~~~~~~~~~~~~~~~~~~ kernel/elfcore.c:22:15: warning: no previous prototype for 'elf_core_extra_data_size' [-Wmissing-prototypes] 22 | size_t __weak elf_core_extra_data_size(void) | ^~~~~~~~~~~~~~~~~~~~~~~~

Provide the include file so gcc is happy, and we don't have potential code drift

Link: http://lkml.kernel.org/r/29875.1565224705@turing-police Signed-off-by: Valdis Kletnieks valdis.kletnieks@vt.edu Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/elfcore.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/kernel/elfcore.c b/kernel/elfcore.c index fc482c8e0bd88..57fb4dcff4349 100644 --- a/kernel/elfcore.c +++ b/kernel/elfcore.c @@ -3,6 +3,7 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/binfmts.h> +#include <linux/elfcore.h>

Elf_Half __weak elf_core_extra_phdrs(void) {

From: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp

[ Upstream commit 7c3a6aedcd6aae0a32a527e68669f7dd667492d1 ]

syzbot found that a thread can stall for minutes inside kexec_load() after that thread was killed by SIGKILL [1]. It turned out that the reproducer was trying to allocate 2408MB of memory using kimage_alloc_page() from kimage_load_normal_segment(). Let's check for SIGKILL before doing memory allocation.

[1] https://syzkaller.appspot.com/bug?id=a0e3436829698d5824231251fad9d8e998f94f5...

Link: http://lkml.kernel.org/r/993c9185-d324-2640-d061-bed2dd18b1f7@I-love.SAKURA.... Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Reported-by: syzbot syzbot+8ab2d0f39fb79fe6ca40@syzkaller.appspotmail.com Cc: Eric Biederman ebiederm@xmission.com Reviewed-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/kexec_core.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index d5870723b8ada..15d70a90b50dc 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -300,6 +300,8 @@ static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order) { struct page *pages;

+ if (fatal_signal_pending(current)) + return NULL; pages = alloc_pages(gfp_mask & ~__GFP_ZERO, order); if (pages) { unsigned int count, i;

From: Allan Zhang allanzhang@google.com

[ Upstream commit 768fb61fcc13b2acaca758275d54c09a65e2968b ]

BPF_PROG_TYPE_SOCK_OPS program can reenter bpf_event_output because it can be called from atomic and non-atomic contexts since we don't have bpf_prog_active to prevent it happen.

This patch enables 3 levels of nesting to support normal, irq and nmi context.

We can easily reproduce the issue by running netperf crr mode with 100 flows and 10 threads from netperf client side.

Here is the whole stack dump:

[ 515.228898] WARNING: CPU: 20 PID: 14686 at kernel/trace/bpf_trace.c:549 bpf_event_output+0x1f9/0x220 [ 515.228903] CPU: 20 PID: 14686 Comm: tcp_crr Tainted: G W 4.15.0-smp-fixpanic #44 [ 515.228904] Hardware name: Intel TBG,ICH10/Ikaria_QC_1b, BIOS 1.22.0 06/04/2018 [ 515.228905] RIP: 0010:bpf_event_output+0x1f9/0x220 [ 515.228906] RSP: 0018:ffff9a57ffc03938 EFLAGS: 00010246 [ 515.228907] RAX: 0000000000000012 RBX: 0000000000000001 RCX: 0000000000000000 [ 515.228907] RDX: 0000000000000000 RSI: 0000000000000096 RDI: ffffffff836b0f80 [ 515.228908] RBP: ffff9a57ffc039c8 R08: 0000000000000004 R09: 0000000000000012 [ 515.228908] R10: ffff9a57ffc1de40 R11: 0000000000000000 R12: 0000000000000002 [ 515.228909] R13: ffff9a57e13bae00 R14: 00000000ffffffff R15: ffff9a57ffc1e2c0 [ 515.228910] FS: 00007f5a3e6ec700(0000) GS:ffff9a57ffc00000(0000) knlGS:0000000000000000 [ 515.228910] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 515.228911] CR2: 0000537082664fff CR3: 000000061fed6002 CR4: 00000000000226f0 [ 515.228911] Call Trace: [ 515.228913] <IRQ> [ 515.228919] [<ffffffff82c6c6cb>] bpf_sockopt_event_output+0x3b/0x50 [ 515.228923] [<ffffffff8265daee>] ? bpf_ktime_get_ns+0xe/0x10 [ 515.228927] [<ffffffff8266fda5>] ? __cgroup_bpf_run_filter_sock_ops+0x85/0x100 [ 515.228930] [<ffffffff82cf90a5>] ? tcp_init_transfer+0x125/0x150 [ 515.228933] [<ffffffff82cf9159>] ? tcp_finish_connect+0x89/0x110 [ 515.228936] [<ffffffff82cf98e4>] ? tcp_rcv_state_process+0x704/0x1010 [ 515.228939] [<ffffffff82c6e263>] ? sk_filter_trim_cap+0x53/0x2a0 [ 515.228942] [<ffffffff82d90d1f>] ? tcp_v6_inbound_md5_hash+0x6f/0x1d0 [ 515.228945] [<ffffffff82d92160>] ? tcp_v6_do_rcv+0x1c0/0x460 [ 515.228947] [<ffffffff82d93558>] ? tcp_v6_rcv+0x9f8/0xb30 [ 515.228951] [<ffffffff82d737c0>] ? ip6_route_input+0x190/0x220 [ 515.228955] [<ffffffff82d5f7ad>] ? ip6_protocol_deliver_rcu+0x6d/0x450 [ 515.228958] [<ffffffff82d60246>] ? ip6_rcv_finish+0xb6/0x170 [ 515.228961] [<ffffffff82d5fb90>] ? ip6_protocol_deliver_rcu+0x450/0x450 [ 515.228963] [<ffffffff82d60361>] ? ipv6_rcv+0x61/0xe0 [ 515.228966] [<ffffffff82d60190>] ? ipv6_list_rcv+0x330/0x330 [ 515.228969] [<ffffffff82c4976b>] ? __netif_receive_skb_one_core+0x5b/0xa0 [ 515.228972] [<ffffffff82c497d1>] ? __netif_receive_skb+0x21/0x70 [ 515.228975] [<ffffffff82c4a8d2>] ? process_backlog+0xb2/0x150 [ 515.228978] [<ffffffff82c4aadf>] ? net_rx_action+0x16f/0x410 [ 515.228982] [<ffffffff830000dd>] ? __do_softirq+0xdd/0x305 [ 515.228986] [<ffffffff8252cfdc>] ? irq_exit+0x9c/0xb0 [ 515.228989] [<ffffffff82e02de5>] ? smp_call_function_single_interrupt+0x65/0x120 [ 515.228991] [<ffffffff82e020e1>] ? call_function_single_interrupt+0x81/0x90 [ 515.228992] </IRQ> [ 515.228996] [<ffffffff82a11ff0>] ? io_serial_in+0x20/0x20 [ 515.229000] [<ffffffff8259c040>] ? console_unlock+0x230/0x490 [ 515.229003] [<ffffffff8259cbaa>] ? vprintk_emit+0x26a/0x2a0 [ 515.229006] [<ffffffff8259cbff>] ? vprintk_default+0x1f/0x30 [ 515.229008] [<ffffffff8259d9f5>] ? vprintk_func+0x35/0x70 [ 515.229011] [<ffffffff8259d4bb>] ? printk+0x50/0x66 [ 515.229013] [<ffffffff82637637>] ? bpf_event_output+0xb7/0x220 [ 515.229016] [<ffffffff82c6c6cb>] ? bpf_sockopt_event_output+0x3b/0x50 [ 515.229019] [<ffffffff8265daee>] ? bpf_ktime_get_ns+0xe/0x10 [ 515.229023] [<ffffffff82c29e87>] ? release_sock+0x97/0xb0 [ 515.229026] [<ffffffff82ce9d6a>] ? tcp_recvmsg+0x31a/0xda0 [ 515.229029] [<ffffffff8266fda5>] ? __cgroup_bpf_run_filter_sock_ops+0x85/0x100 [ 515.229032] [<ffffffff82ce77c1>] ? tcp_set_state+0x191/0x1b0 [ 515.229035] [<ffffffff82ced10e>] ? tcp_disconnect+0x2e/0x600 [ 515.229038] [<ffffffff82cecbbb>] ? tcp_close+0x3eb/0x460 [ 515.229040] [<ffffffff82d21082>] ? inet_release+0x42/0x70 [ 515.229043] [<ffffffff82d58809>] ? inet6_release+0x39/0x50 [ 515.229046] [<ffffffff82c1f32d>] ? __sock_release+0x4d/0xd0 [ 515.229049] [<ffffffff82c1f3e5>] ? sock_close+0x15/0x20 [ 515.229052] [<ffffffff8273b517>] ? __fput+0xe7/0x1f0 [ 515.229055] [<ffffffff8273b66e>] ? ____fput+0xe/0x10 [ 515.229058] [<ffffffff82547bf2>] ? task_work_run+0x82/0xb0 [ 515.229061] [<ffffffff824086df>] ? exit_to_usermode_loop+0x7e/0x11f [ 515.229064] [<ffffffff82408171>] ? do_syscall_64+0x111/0x130 [ 515.229067] [<ffffffff82e0007c>] ? entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: a5a3a828cd00 ("bpf: add perf event notificaton support for sock_ops") Signed-off-by: Allan Zhang allanzhang@google.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Stanislav Fomichev sdf@google.com Reviewed-by: Eric Dumazet edumazet@google.com Acked-by: John Fastabend john.fastabend@gmail.com Link: https://lore.kernel.org/bpf/20190925234312.94063-2-allanzhang@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/trace/bpf_trace.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ca1255d145766..3e38a010003c9 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -500,14 +500,17 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

-static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs); -static DEFINE_PER_CPU(struct perf_sample_data, bpf_misc_sd); +static DEFINE_PER_CPU(int, bpf_event_output_nest_level); +struct bpf_nested_pt_regs { + struct pt_regs regs[3]; +}; +static DEFINE_PER_CPU(struct bpf_nested_pt_regs, bpf_pt_regs); +static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds);

u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { - struct perf_sample_data *sd = this_cpu_ptr(&bpf_misc_sd); - struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs); + int nest_level = this_cpu_inc_return(bpf_event_output_nest_level); struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, @@ -522,12 +525,25 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, .data = meta, }, }; + struct perf_sample_data *sd; + struct pt_regs *regs; + u64 ret; + + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) { + ret = -EBUSY; + goto out; + } + sd = this_cpu_ptr(&bpf_misc_sds.sds[nest_level - 1]); + regs = this_cpu_ptr(&bpf_pt_regs.regs[nest_level - 1]);

perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); sd->raw = &raw;

- return __bpf_perf_event_output(regs, map, flags, sd); + ret = __bpf_perf_event_output(regs, map, flags, sd); +out: + this_cpu_dec(bpf_event_output_nest_level); + return ret; }

BPF_CALL_0(bpf_get_current_task)

From: Marek Vasut marex@denx.de

[ Upstream commit a3aa6e65beebf3780026753ebf39db19f4c92990 ]

The regmap stride is set to 1 for regmap describing 8bit registers already. However, for 16/32/64bit registers, the stride is 2/4/8 respectively. This is not correct, as the switch protocol supports unaligned register reads and writes and the KSZ87xx even uses such unaligned register accesses to read e.g. MIB counter.

This patch fixes MIB counter access on KSZ87xx.

Signed-off-by: Marek Vasut marex@denx.de Cc: Andrew Lunn andrew@lunn.ch Cc: David S. Miller davem@davemloft.net Cc: Florian Fainelli f.fainelli@gmail.com Cc: George McCollister george.mccollister@gmail.com Cc: Tristram Ha Tristram.Ha@microchip.com Cc: Vivien Didelot vivien.didelot@savoirfairelinux.com Cc: Woojung Huh woojung.huh@microchip.com Fixes: 46558d601cb6 ("net: dsa: microchip: Initial SPI regmap support") Fixes: 255b59ad0db2 ("net: dsa: microchip: Factor out regmap config generation into common header") Reviewed-by: George McCollister george.mccollister@gmail.com Tested-by: George McCollister george.mccollister@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/microchip/ksz_common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 72ec250b95408..823f544add0a3 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -130,7 +130,7 @@ static inline void ksz_pwrite32(struct ksz_device *dev, int port, int offset, { \ .name = #width, \ .val_bits = (width), \ - .reg_stride = (width) / 8, \ + .reg_stride = 1, \ .reg_bits = (regbits) + (regalign), \ .pad_bits = (regpad), \ .max_register = BIT(regbits) - 1, \

From: Arnaldo Carvalho de Melo acme@redhat.com

[ Upstream commit 26acf400d2dcc72c7e713e1f55db47ad92010cc2 ]

Naresh Kamboju reported, that on the i386 build pr_err() doesn't get defined properly due to header ordering:

perf-in.o: In function `libunwind__x86_reg_id': tools/perf/util/libunwind/../../arch/x86/util/unwind-libunwind.c:109: undefined reference to `pr_err'

Reported-by: Naresh Kamboju naresh.kamboju@linaro.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Cc: David Ahern dsahern@gmail.com Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/arch/x86/util/unwind-libunwind.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 05920e3edf7a7..47357973b55b2 100644 --- a/tools/perf/arch/x86/util/unwind-libunwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0

#include <errno.h> +#include "../../util/debug.h" #ifndef REMOTE_UNWIND_LIBUNWIND #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" -#include "../../util/debug.h" #endif

#ifdef HAVE_ARCH_X86_64_SUPPORT

From: Thierry Reding treding@nvidia.com

[ Upstream commit 4f28bd956e081fc018fe9b41ffa31573f17bfb61 ]

The size of individual pages in the page pool in given by an order. The order is the binary logarithm of the number of pages that make up one of the pages in the pool. However, the driver currently passes the number of pages rather than the order, so it ends up wasting quite a bit of memory.

Fix this by taking the binary logarithm and passing that in the order field.

Fixes: 2af6106ae949 ("net: stmmac: Introducing support for Page Pool") Signed-off-by: Thierry Reding treding@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b19ab09cb18f7..5c4408bdc843a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1532,13 +1532,15 @@ static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv) for (queue = 0; queue < rx_count; queue++) { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; struct page_pool_params pp_params = { 0 }; + unsigned int num_pages;

rx_q->queue_index = queue; rx_q->priv_data = priv;

pp_params.flags = PP_FLAG_DMA_MAP; pp_params.pool_size = DMA_RX_SIZE; - pp_params.order = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE); + num_pages = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE); + pp_params.order = ilog2(num_pages); pp_params.nid = dev_to_node(priv->device); pp_params.dev = priv->device; pp_params.dma_dir = DMA_FROM_DEVICE;

From: Danielle Ratson danieller@mellanox.com

[ Upstream commit 52feb8b588f6d23673dd7cc2b44b203493b627f6 ]

The ASIC can only mirror a packet to one port, but when user is trying to set more than one mirror action, it doesn't fail.

Add a check if more than one mirror action was specified per rule and if so, fail for not being supported.

Fixes: d0d13c1858a11 ("mlxsw: spectrum_acl: Add support for mirror action") Signed-off-by: Danielle Ratson danieller@mellanox.com Acked-by: Jiri Pirko jiri@mellanox.com Signed-off-by: Ido Schimmel idosch@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 202e9a2460194..7c13656a83384 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -21,6 +21,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, struct netlink_ext_ack *extack) { const struct flow_action_entry *act; + int mirror_act_count = 0; int err, i;

if (!flow_action_has_entries(flow_action)) @@ -95,6 +96,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, case FLOW_ACTION_MIRRED: { struct net_device *out_dev = act->dev;

+ if (mirror_act_count++) { + NL_SET_ERR_MSG_MOD(extack, "Multiple mirror actions per rule are not supported"); + return -EOPNOTSUPP; + } + err = mlxsw_sp_acl_rulei_act_mirror(mlxsw_sp, rulei, block, out_dev, extack);

From: Navid Emamdoost navid.emamdoost@gmail.com

[ Upstream commit 8572cea1461a006bce1d06c0c4b0575869125fa4 ]

In nfp_flower_spawn_phy_reprs, in the for loop over eth_tbl if any of intermediate allocations or initializations fail memory is leaked. requiered releases are added.

Fixes: b94524529741 ("nfp: flower: add per repr private data for LAG offload") Signed-off-by: Navid Emamdoost navid.emamdoost@gmail.com Acked-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/netronome/nfp/flower/main.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index 5331e01f373e0..acb02e1513f2e 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -518,6 +518,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv) repr_priv = kzalloc(sizeof(*repr_priv), GFP_KERNEL); if (!repr_priv) { err = -ENOMEM; + nfp_repr_free(repr); goto err_reprs_clean; }

@@ -528,11 +529,13 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv) port = nfp_port_alloc(app, NFP_PORT_PHYS_PORT, repr); if (IS_ERR(port)) { err = PTR_ERR(port); + kfree(repr_priv); nfp_repr_free(repr); goto err_reprs_clean; } err = nfp_port_init_phy_port(app->pf, app, port, i); if (err) { + kfree(repr_priv); nfp_port_free(port); nfp_repr_free(repr); goto err_reprs_clean; @@ -545,6 +548,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv) err = nfp_repr_init(app, repr, cmsg_port_id, port, priv->nn->dp.netdev); if (err) { + kfree(repr_priv); nfp_port_free(port); nfp_repr_free(repr); goto err_reprs_clean;

From: Eric Biggers ebiggers@google.com

[ Upstream commit 76e43c8ccaa35c30d5df853013561145a0f750a5 ]

When IOCB_CMD_POLL is used on the FUSE device, aio_poll() disables IRQs and takes kioctx::ctx_lock, then fuse_iqueue::waitq.lock.

This may have to wait for fuse_iqueue::waitq.lock to be released by one of many places that take it with IRQs enabled. Since the IRQ handler may take kioctx::ctx_lock, lockdep reports that a deadlock is possible.

Fix it by protecting the state of struct fuse_iqueue with a separate spinlock, and only accessing fuse_iqueue::waitq using the versions of the waitqueue functions which do IRQ-safe locking internally.

Reproducer:

#include <fcntl.h> #include <stdio.h> #include <sys/mount.h> #include <sys/stat.h> #include <sys/syscall.h> #include <unistd.h> #include <linux/aio_abi.h>

int main() { char opts[128]; int fd = open("/dev/fuse", O_RDWR); aio_context_t ctx = 0; struct iocb cb = { .aio_lio_opcode = IOCB_CMD_POLL, .aio_fildes = fd }; struct iocb *cbp = &cb;

sprintf(opts, "fd=%d,rootmode=040000,user_id=0,group_id=0", fd); mkdir("mnt", 0700); mount("foo", "mnt", "fuse", 0, opts); syscall(__NR_io_setup, 1, &ctx); syscall(__NR_io_submit, ctx, 1, &cbp); }

Beginning of lockdep output:

===================================================== WARNING: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected 5.3.0-rc5 #9 Not tainted ----------------------------------------------------- syz_fuse/135 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: 000000003590ceda (&fiq->waitq){+.+.}, at: spin_lock include/linux/spinlock.h:338 [inline] 000000003590ceda (&fiq->waitq){+.+.}, at: aio_poll fs/aio.c:1751 [inline] 000000003590ceda (&fiq->waitq){+.+.}, at: __io_submit_one.constprop.0+0x203/0x5b0 fs/aio.c:1825

and this task is already holding: 0000000075037284 (&(&ctx->ctx_lock)->rlock){..-.}, at: spin_lock_irq include/linux/spinlock.h:363 [inline] 0000000075037284 (&(&ctx->ctx_lock)->rlock){..-.}, at: aio_poll fs/aio.c:1749 [inline] 0000000075037284 (&(&ctx->ctx_lock)->rlock){..-.}, at: __io_submit_one.constprop.0+0x1f4/0x5b0 fs/aio.c:1825 which would create a new lock dependency: (&(&ctx->ctx_lock)->rlock){..-.} -> (&fiq->waitq){+.+.}

but this new dependency connects a SOFTIRQ-irq-safe lock: (&(&ctx->ctx_lock)->rlock){..-.}

[...]

Reported-by: syzbot+af05535bb79520f95431@syzkaller.appspotmail.com Reported-by: syzbot+d86c4426a01f60feddc7@syzkaller.appspotmail.com Fixes: bfe4037e722e ("aio: implement IOCB_CMD_POLL") Cc: stable@vger.kernel.org # v4.19+ Cc: Christoph Hellwig hch@lst.de Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/fuse/dev.c | 93 +++++++++++++++++++++++++----------------------- fs/fuse/fuse_i.h | 3 ++ fs/fuse/inode.c | 1 + 3 files changed, 52 insertions(+), 45 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index ea8237513dfaf..186468fba82e4 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -377,7 +377,7 @@ static void queue_request(struct fuse_iqueue *fiq, struct fuse_req *req) req->in.h.len = sizeof(struct fuse_in_header) + len_args(req->in.numargs, (struct fuse_arg *) req->in.args); list_add_tail(&req->list, &fiq->pending); - wake_up_locked(&fiq->waitq); + wake_up(&fiq->waitq); kill_fasync(&fiq->fasync, SIGIO, POLL_IN); }

@@ -389,16 +389,16 @@ void fuse_queue_forget(struct fuse_conn *fc, struct fuse_forget_link *forget, forget->forget_one.nodeid = nodeid; forget->forget_one.nlookup = nlookup;

- spin_lock(&fiq->waitq.lock); + spin_lock(&fiq->lock); if (fiq->connected) { fiq->forget_list_tail->next = forget; fiq->forget_list_tail = forget; - wake_up_locked(&fiq->waitq); + wake_up(&fiq->waitq); kill_fasync(&fiq->fasync, SIGIO, POLL_IN); } else { kfree(forget); } - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); }

static void flush_bg_queue(struct fuse_conn *fc) @@ -412,10 +412,10 @@ static void flush_bg_queue(struct fuse_conn *fc) req = list_first_entry(&fc->bg_queue, struct fuse_req, list); list_del(&req->list); fc->active_background++; - spin_lock(&fiq->waitq.lock); + spin_lock(&fiq->lock); req->in.h.unique = fuse_get_unique(fiq); queue_request(fiq, req); - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); } }

@@ -439,9 +439,9 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) * smp_mb() from queue_interrupt(). */ if (!list_empty(&req->intr_entry)) { - spin_lock(&fiq->waitq.lock); + spin_lock(&fiq->lock); list_del_init(&req->intr_entry); - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); } WARN_ON(test_bit(FR_PENDING, &req->flags)); WARN_ON(test_bit(FR_SENT, &req->flags)); @@ -483,10 +483,10 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)

static int queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) { - spin_lock(&fiq->waitq.lock); + spin_lock(&fiq->lock); /* Check for we've sent request to interrupt this req */ if (unlikely(!test_bit(FR_INTERRUPTED, &req->flags))) { - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); return -EINVAL; }

@@ -499,13 +499,13 @@ static int queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) smp_mb(); if (test_bit(FR_FINISHED, &req->flags)) { list_del_init(&req->intr_entry); - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); return 0; } - wake_up_locked(&fiq->waitq); + wake_up(&fiq->waitq); kill_fasync(&fiq->fasync, SIGIO, POLL_IN); } - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); return 0; }

@@ -535,16 +535,16 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req) if (!err) return;

- spin_lock(&fiq->waitq.lock); + spin_lock(&fiq->lock); /* Request is not yet in userspace, bail out */ if (test_bit(FR_PENDING, &req->flags)) { list_del(&req->list); - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); __fuse_put_request(req); req->out.h.error = -EINTR; return; } - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); }

/* @@ -559,9 +559,9 @@ static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req) struct fuse_iqueue *fiq = &fc->iq;

BUG_ON(test_bit(FR_BACKGROUND, &req->flags)); - spin_lock(&fiq->waitq.lock); + spin_lock(&fiq->lock); if (!fiq->connected) { - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); req->out.h.error = -ENOTCONN; } else { req->in.h.unique = fuse_get_unique(fiq); @@ -569,7 +569,7 @@ static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req) /* acquire extra reference, since request is still needed after request_end() */ __fuse_get_request(req); - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock);

request_wait_answer(fc, req); /* Pairs with smp_wmb() in request_end() */ @@ -700,12 +700,12 @@ static int fuse_request_send_notify_reply(struct fuse_conn *fc,

__clear_bit(FR_ISREPLY, &req->flags); req->in.h.unique = unique; - spin_lock(&fiq->waitq.lock); + spin_lock(&fiq->lock); if (fiq->connected) { queue_request(fiq, req); err = 0; } - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock);

return err; } @@ -1149,12 +1149,12 @@ static int request_pending(struct fuse_iqueue *fiq) * Unlike other requests this is assembled on demand, without a need * to allocate a separate fuse_req structure. * - * Called with fiq->waitq.lock held, releases it + * Called with fiq->lock held, releases it */ static int fuse_read_interrupt(struct fuse_iqueue *fiq, struct fuse_copy_state *cs, size_t nbytes, struct fuse_req *req) -__releases(fiq->waitq.lock) +__releases(fiq->lock) { struct fuse_in_header ih; struct fuse_interrupt_in arg; @@ -1169,7 +1169,7 @@ __releases(fiq->waitq.lock) ih.unique = (req->in.h.unique | FUSE_INT_REQ_BIT); arg.unique = req->in.h.unique;

- spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); if (nbytes < reqsize) return -EINVAL;

@@ -1206,7 +1206,7 @@ static struct fuse_forget_link *dequeue_forget(struct fuse_iqueue *fiq, static int fuse_read_single_forget(struct fuse_iqueue *fiq, struct fuse_copy_state *cs, size_t nbytes) -__releases(fiq->waitq.lock) +__releases(fiq->lock) { int err; struct fuse_forget_link *forget = dequeue_forget(fiq, 1, NULL); @@ -1220,7 +1220,7 @@ __releases(fiq->waitq.lock) .len = sizeof(ih) + sizeof(arg), };

- spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); kfree(forget); if (nbytes < ih.len) return -EINVAL; @@ -1238,7 +1238,7 @@ __releases(fiq->waitq.lock)

static int fuse_read_batch_forget(struct fuse_iqueue *fiq, struct fuse_copy_state *cs, size_t nbytes) -__releases(fiq->waitq.lock) +__releases(fiq->lock) { int err; unsigned max_forgets; @@ -1252,13 +1252,13 @@ __releases(fiq->waitq.lock) };

if (nbytes < ih.len) { - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); return -EINVAL; }

max_forgets = (nbytes - ih.len) / sizeof(struct fuse_forget_one); head = dequeue_forget(fiq, max_forgets, &count); - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock);

arg.count = count; ih.len += count * sizeof(struct fuse_forget_one); @@ -1288,7 +1288,7 @@ __releases(fiq->waitq.lock) static int fuse_read_forget(struct fuse_conn *fc, struct fuse_iqueue *fiq, struct fuse_copy_state *cs, size_t nbytes) -__releases(fiq->waitq.lock) +__releases(fiq->lock) { if (fc->minor < 16 || fiq->forget_list_head.next->next == NULL) return fuse_read_single_forget(fiq, cs, nbytes); @@ -1318,16 +1318,19 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, unsigned int hash;

restart: - spin_lock(&fiq->waitq.lock); - err = -EAGAIN; - if ((file->f_flags & O_NONBLOCK) && fiq->connected && - !request_pending(fiq)) - goto err_unlock; + for (;;) { + spin_lock(&fiq->lock); + if (!fiq->connected || request_pending(fiq)) + break; + spin_unlock(&fiq->lock);

- err = wait_event_interruptible_exclusive_locked(fiq->waitq, + if (file->f_flags & O_NONBLOCK) + return -EAGAIN; + err = wait_event_interruptible_exclusive(fiq->waitq, !fiq->connected || request_pending(fiq)); - if (err) - goto err_unlock; + if (err) + return err; + }

if (!fiq->connected) { err = fc->aborted ? -ECONNABORTED : -ENODEV; @@ -1351,7 +1354,7 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, req = list_entry(fiq->pending.next, struct fuse_req, list); clear_bit(FR_PENDING, &req->flags); list_del_init(&req->list); - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock);

in = &req->in; reqsize = in->h.len; @@ -1409,7 +1412,7 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, return err;

err_unlock: - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock); return err; }

@@ -2121,12 +2124,12 @@ static __poll_t fuse_dev_poll(struct file *file, poll_table *wait) fiq = &fud->fc->iq; poll_wait(file, &fiq->waitq, wait);

- spin_lock(&fiq->waitq.lock); + spin_lock(&fiq->lock); if (!fiq->connected) mask = EPOLLERR; else if (request_pending(fiq)) mask |= EPOLLIN | EPOLLRDNORM; - spin_unlock(&fiq->waitq.lock); + spin_unlock(&fiq->lock);

return mask; } @@ -2221,15 +2224,15 @@ void fuse_abort_conn(struct fuse_conn *fc) flush_bg_queue(fc); spin_unlock(&fc->bg_lock);

- spin_lock(&fiq->waitq.lock); + spin_lock(&fiq->lock); fiq->connected = 0; list_for_each_entry(req, &fiq->pending, list) clear_bit(FR_PENDING, &req->flags); list_splice_tail_init(&fiq->pending, &to_end); while (forget_pending(fiq)) kfree(dequeue_forget(fiq, 1, NULL)); - wake_up_all_locked(&fiq->waitq); - spin_unlock(&fiq->waitq.lock); + wake_up_all(&fiq->waitq); + spin_unlock(&fiq->lock); kill_fasync(&fiq->fasync, SIGIO, POLL_IN); end_polls(fc); wake_up_all(&fc->blocked_waitq); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 24dbca7777751..89bdc41e0d86b 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -450,6 +450,9 @@ struct fuse_iqueue { /** Connection established */ unsigned connected;

+ /** Lock protecting accesses to members of this structure */ + spinlock_t lock; + /** Readers of the connection are waiting on this */ wait_queue_head_t waitq;

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 04b10b3b8741b..f3104db3de83a 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -582,6 +582,7 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root) static void fuse_iqueue_init(struct fuse_iqueue *fiq) { memset(fiq, 0, sizeof(struct fuse_iqueue)); + spin_lock_init(&fiq->lock); init_waitqueue_head(&fiq->waitq); INIT_LIST_HEAD(&fiq->pending); INIT_LIST_HEAD(&fiq->interrupts);

From: Oliver Neukum oneukum@suse.com

[ Upstream commit 280ceaed79f18db930c0cc8bb21f6493490bf29c ]

After a reset packet sizes and device mtu can change and need to be reevaluated to calculate queue sizes. Malicious devices can set this to zero and we divide by it. Introduce sanity checking.

Reported-and-tested-by: syzbot+6102c120be558c885f04@syzkaller.appspotmail.com Signed-off-by: Oliver Neukum oneukum@suse.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/usbnet.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 07c00e378a5cd..ef1d667b0108b 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -344,6 +344,8 @@ void usbnet_update_max_qlen(struct usbnet *dev) { enum usb_device_speed speed = dev->udev->speed;

+ if (!dev->rx_urb_size || !dev->hard_mtu) + goto insanity; switch (speed) { case USB_SPEED_HIGH: dev->rx_qlen = MAX_QUEUE_MEMORY / dev->rx_urb_size; @@ -360,6 +362,7 @@ void usbnet_update_max_qlen(struct usbnet *dev) dev->tx_qlen = 5 * MAX_QUEUE_MEMORY / dev->hard_mtu; break; default: +insanity: dev->rx_qlen = dev->tx_qlen = 4; } }

From: Filipe Manana fdmanana@suse.com

[ Upstream commit 9f7fec0ba89108b9385f1b9fb167861224912a4a ]

Some of the self tests create a test inode, setup some extents and then do calls to btrfs_get_extent() to test that the corresponding extent maps exist and are correct. However btrfs_get_extent(), since the 5.2 merge window, now errors out when it finds a regular or prealloc extent for an inode that does not correspond to a regular file (its ->i_mode is not S_IFREG). This causes the self tests to fail sometimes, specially when KASAN, slub_debug and page poisoning are enabled:

$ modprobe btrfs modprobe: ERROR: could not insert 'btrfs': Invalid argument

$ dmesg [ 9414.691648] Btrfs loaded, crc32c=crc32c-intel, debug=on, assert=on, integrity-checker=on, ref-verify=on [ 9414.692655] BTRFS: selftest: sectorsize: 4096 nodesize: 4096 [ 9414.692658] BTRFS: selftest: running btrfs free space cache tests [ 9414.692918] BTRFS: selftest: running extent only tests [ 9414.693061] BTRFS: selftest: running bitmap only tests [ 9414.693366] BTRFS: selftest: running bitmap and extent tests [ 9414.696455] BTRFS: selftest: running space stealing from bitmap to extent tests [ 9414.697131] BTRFS: selftest: running extent buffer operation tests [ 9414.697133] BTRFS: selftest: running btrfs_split_item tests [ 9414.697564] BTRFS: selftest: running extent I/O tests [ 9414.697583] BTRFS: selftest: running find delalloc tests [ 9415.081125] BTRFS: selftest: running find_first_clear_extent_bit test [ 9415.081278] BTRFS: selftest: running extent buffer bitmap tests [ 9415.124192] BTRFS: selftest: running inode tests [ 9415.124195] BTRFS: selftest: running btrfs_get_extent tests [ 9415.127909] BTRFS: selftest: running hole first btrfs_get_extent test [ 9415.128343] BTRFS critical (device (efault)): regular/prealloc extent found for non-regular inode 256 [ 9415.131428] BTRFS: selftest: fs/btrfs/tests/inode-tests.c:904 expected a real extent, got 0

This happens because the test inodes are created without ever initializing the i_mode field of the inode, and neither VFS's new_inode() nor the btrfs callback btrfs_alloc_inode() initialize the i_mode. Initialization of the i_mode is done through the various callbacks used by the VFS to create new inodes (regular files, directories, symlinks, tmpfiles, etc), which all call btrfs_new_inode() which in turn calls inode_init_owner(), which sets the inode's i_mode. Since the tests only uses new_inode() to create the test inodes, the i_mode was never initialized.

This always happens on a VM I used with kasan, slub_debug and many other debug facilities enabled. It also happened to someone who reported this on bugzilla (on a 5.3-rc).

Fix this by setting i_mode to S_IFREG at btrfs_new_test_inode().

Fixes: 6bf9e4bd6a2778 ("btrfs: inode: Verify inode mode to avoid NULL pointer dereference") Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204397 Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: Qu Wenruo wqu@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/tests/btrfs-tests.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 1e3ba49493995..814a918998ece 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -51,7 +51,13 @@ static struct file_system_type test_type = {

struct inode *btrfs_new_test_inode(void) { - return new_inode(test_mnt->mnt_sb); + struct inode *inode; + + inode = new_inode(test_mnt->mnt_sb); + if (inode) + inode_init_owner(inode, NULL, S_IFREG); + + return inode; }

static int btrfs_init_test_fs(void)